AI agents call locals to retrieve information from Rr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays data (local variables and their metadata) from a debugger session without creating, modifying, deleting, or executing anything. It is a passive inspection operation typical of debugging interfaces. The context of a reverse debugger does not change its fundamental nature as a read operation.
From the tool's definition Tool name 'locals' and description 'Get all local variables in the current stack frame with their values and types' indicate a read-only query operation that retrieves debugging information without modifying any state.
Attacks that exploit this kind of access
Get all local variables in the current stack frame with their values and types. It is categorised as a Read tool in the Rr MCP Server, which means it retrieves data without modifying state.
Register the Rr MCP server in PolicyLayer and add a rule for locals: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Rr. Nothing to install.
locals is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the locals rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for locals. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
locals is provided by the Rr MCP server (jnjaeschke/rr-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →